How to Use the UnifyApps MCP in OpenAI Agents SDK

Q: How do I check my setup using UnifyApps and OpenAI Agents SDK?

To see what's connected, call listintegrations. For a detailed audit, you can follow up with getintegrationdetails on any specific service. This gives your agent the full context it needs.

Q: Can I track flow history with UnifyApps and OpenAI Agents SDK?

Yes. The listflowexecutions tool lists recent run histories for all automation flows. It's a direct way to verify if an agent successfully executed its tasks.

Q: What information does UnifyApps provide to OpenAI Agents SDK?

The MCP Server provides tools like listautomationflows and listactiveconnections. This allows your agent to understand the current scope of automated processes and live data access.

Automate complex workflows instantly using your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UnifyApps MCP to OpenAI Agents SDK

Create your Vinkius account to connect UnifyApps to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup UnifyApps with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit all platform integrations.

Use `list_integrations` to pull a complete list of everything connected in UnifyApps. You'll see every configured integration, which is crucial for auditing what data sources your agent can touch. Need to know if connections are live? Run `list_active_connections`. This shows the current status of all accounts and links, letting you verify access before starting a flow.

Monitor automation setup.

`list_automation_flows` pulls up every single automated process defined on UnifyApps. You can check these flows to make sure the intended logic is in place for your production agent system. Want to see what happened last week? `list_flow_executions` gives you a history of recent runs, letting you trace failures or confirm success rates.

Check AI agents and details.

`list_ai_agents` pulls up all the specialized agents configured in your environment. This helps keep track of who's running what within UnifyApps. You can also run `get_integration_details` to get deep info on a specific connection, verifying exactly how that integration is set up.

Setup guide

Set up UnifyApps MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all UnifyApps tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives UnifyApps tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate UnifyApps tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="UnifyApps Agent",
            instructions="You have access to UnifyApps tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by UnifyApps. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect UnifyApps now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about UnifyApps MCP in OpenAI Agents SDK

To see what's connected, call `list_integrations`. For a detailed audit, you can follow up with `get_integration_details` on any specific service. This gives your agent the full context it needs.

Yes. The `list_flow_executions` tool lists recent run histories for all automation flows. It's a direct way to verify if an agent successfully executed its tasks.

The MCP Server provides tools like `list_automation_flows` and `list_active_connections`. This allows your agent to understand the current scope of automated processes and live data access.

Absolutely. Your agent auto-discovers all available tools, like `list_ai_agents` and `list_integrations`. It can chain these operations together to complete complex tasks.

UnifyApps exposes connection status and flow definitions. Your agent reads this metadata, such as which accounts are connected via `list_active_connections`, but it doesn't handle raw user content.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript